/* SPDX-License-Identifier: GPL-2.0 */
/*
 * arch/alpha/lib/ev6-stxncpy.S
 * 21264 version contributed by Rick Gorton <rick.gorton@api-networks.com>
 *
 * Copy no more than COUNT bytes of the null-terminated string from
 * SRC to DST.
 *
 * This is an internal routine used by strncpy, stpncpy, and strncat.
 * As such, it uses special linkage conventions to make implementation
 * of these public functions more efficient.
 *
 * On input:
 *      t9 = return address
 *      a0 = DST
 *      a1 = SRC
 *      a2 = COUNT
 *
 * Furthermore, COUNT may not be zero.
 *
 * On output:
 *      t0  = last word written
 *      t10 = bitmask (with one bit set) indicating the byte position of
 *            the end of the range specified by COUNT
 *      t12 = bitmask (with one bit set) indicating the last byte written
 *      a0  = unaligned address of the last *word* written
 *      a2  = the number of full words left in COUNT
 *
 * Furthermore, v0, a3-a5, t11, and $at are untouched.
 *
 * Much of the information about 21264 scheduling/coding comes from:
 *      Compiler Writer's Guide for the Alpha 21264
 *      abbreviated as 'CWG' in other comments here
 *      ftp.digital.com/pub/Digital/info/semiconductor/literature/dsc-library.html
 * Scheduling notation:
 *      E       - either cluster
 *      U       - upper subcluster; U0 - subcluster U0; U1 - subcluster U1
 *      L       - lower subcluster; L0 - subcluster L0; L1 - subcluster L1
 * Try not to change the actual algorithm if possible for consistency.
 */

#include <asm/regdef.h>

        .set noat
        .set noreorder

        .text

/* There is a problem with either gdb (as of 4.16) or gas (as of 2.7) that
   doesn't like putting the entry point for a procedure somewhere in the
   middle of the procedure descriptor.  Work around this by putting the
   aligned copy in its own procedure descriptor */


        .ent stxncpy_aligned
        .align 4
stxncpy_aligned:
        .frame sp, 0, t9, 0
        .prologue 0

        /* On entry to this basic block:
           t0 == the first destination word for masking back in
           t1 == the first source word.  */

        /* Create the 1st output word and detect 0's in the 1st input word.  */
        lda     t2, -1          # E : build a mask against false zero
        mskqh   t2, a1, t2      # U :   detection in the src word (stall)
        mskqh   t1, a1, t3      # U :
        ornot   t1, t2, t2      # E : (stall)

        mskql   t0, a1, t0      # U : assemble the first output word
        cmpbge  zero, t2, t8    # E : bits set iff null found
        or      t0, t3, t0      # E : (stall)
        beq     a2, $a_eoc      # U :

        bne     t8, $a_eos      # U :
        nop
        nop
        nop

        /* On entry to this basic block:
           t0 == a source word not containing a null.  */

        /*
         * nops here to:
         *      separate store quads from load quads
         *      limit of 1 bcond/quad to permit training
         */
$a_loop:
        stq_u   t0, 0(a0)       # L :
        addq    a0, 8, a0       # E :
        subq    a2, 1, a2       # E :
        nop

        ldq_u   t0, 0(a1)       # L :
        addq    a1, 8, a1       # E :
        cmpbge  zero, t0, t8    # E :
        beq     a2, $a_eoc      # U :

        beq     t8, $a_loop     # U :
        nop
        nop
        nop

        /* Take care of the final (partial) word store.  At this point
           the end-of-count bit is set in t8 iff it applies.

           On entry to this basic block we have:
           t0 == the source word containing the null
           t8 == the cmpbge mask that found it.  */

$a_eos:
        negq    t8, t12         # E : find low bit set
        and     t8, t12, t12    # E : (stall)
        /* For the sake of the cache, don't read a destination word
           if we're not going to need it.  */
        and     t12, 0x80, t6   # E : (stall)
        bne     t6, 1f          # U : (stall)

        /* We're doing a partial word store and so need to combine
           our source and original destination words.  */
        ldq_u   t1, 0(a0)       # L :
        subq    t12, 1, t6      # E :
        or      t12, t6, t8     # E : (stall)
        zapnot  t0, t8, t0      # U : clear src bytes > null (stall)

        zap     t1, t8, t1      # .. e1 : clear dst bytes <= null
        or      t0, t1, t0      # e1    : (stall)
        nop
        nop

1:      stq_u   t0, 0(a0)       # L :
        ret     (t9)            # L0 : Latency=3
        nop
        nop

        /* Add the end-of-count bit to the eos detection bitmask.  */
$a_eoc:
        or      t10, t8, t8     # E :
        br      $a_eos          # L0 : Latency=3
        nop
        nop

        .end stxncpy_aligned

        .align 4
        .ent __stxncpy
        .globl __stxncpy
__stxncpy:
        .frame sp, 0, t9, 0
        .prologue 0

        /* Are source and destination co-aligned?  */
        xor     a0, a1, t1      # E :
        and     a0, 7, t0       # E : find dest misalignment
        and     t1, 7, t1       # E : (stall)
        addq    a2, t0, a2      # E : bias count by dest misalignment (stall)

        subq    a2, 1, a2       # E :
        and     a2, 7, t2       # E : (stall)
        srl     a2, 3, a2       # U : a2 = loop counter = (count - 1)/8 (stall)
        addq    zero, 1, t10    # E :

        sll     t10, t2, t10    # U : t10 = bitmask of last count byte
        bne     t1, $unaligned  # U :
        /* We are co-aligned; take care of a partial first word.  */
        ldq_u   t1, 0(a1)       # L : load first src word
        addq    a1, 8, a1       # E :

        beq     t0, stxncpy_aligned     # U : avoid loading dest word if not needed
        ldq_u   t0, 0(a0)       # L :
        nop
        nop

        br      stxncpy_aligned # .. e1 :
        nop
        nop
        nop



/* The source and destination are not co-aligned.  Align the destination
   and cope.  We have to be very careful about not reading too much and
   causing a SEGV.  */

        .align 4
$u_head:
        /* We know just enough now to be able to assemble the first
           full source word.  We can still find a zero at the end of it
           that prevents us from outputting the whole thing.

           On entry to this basic block:
           t0 == the first dest word, unmasked
           t1 == the shifted low bits of the first source word
           t6 == bytemask that is -1 in dest word bytes */

        ldq_u   t2, 8(a1)       # L : Latency=3 load second src word
        addq    a1, 8, a1       # E :
        mskql   t0, a0, t0      # U : mask trailing garbage in dst
        extqh   t2, a1, t4      # U : (3 cycle stall on t2)

        or      t1, t4, t1      # E : first aligned src word complete (stall)
        mskqh   t1, a0, t1      # U : mask leading garbage in src (stall)
        or      t0, t1, t0      # E : first output word complete (stall)
        or      t0, t6, t6      # E : mask original data for zero test (stall)

        cmpbge  zero, t6, t8    # E :
        beq     a2, $u_eocfin   # U :
        lda     t6, -1          # E :
        nop

        bne     t8, $u_final    # U :
        mskql   t6, a1, t6      # U : mask out bits already seen
        stq_u   t0, 0(a0)       # L : store first output word
        or      t6, t2, t2      # E : (stall)

        cmpbge  zero, t2, t8    # E : find nulls in second partial
        addq    a0, 8, a0       # E :
        subq    a2, 1, a2       # E :
        bne     t8, $u_late_head_exit   # U :

        /* Finally, we've got all the stupid leading edge cases taken care
           of and we can set up to enter the main loop.  */
        extql   t2, a1, t1      # U : position hi-bits of lo word
        beq     a2, $u_eoc      # U :
        ldq_u   t2, 8(a1)       # L : read next high-order source word
        addq    a1, 8, a1       # E :

        extqh   t2, a1, t0      # U : position lo-bits of hi word (stall)
        cmpbge  zero, t2, t8    # E :
        nop
        bne     t8, $u_eos      # U :

        /* Unaligned copy main loop.  In order to avoid reading too much,
           the loop is structured to detect zeros in aligned source words.
           This has, unfortunately, effectively pulled half of a loop
           iteration out into the head and half into the tail, but it does
           prevent nastiness from accumulating in the very thing we want
           to run as fast as possible.

           On entry to this basic block:
           t0 == the shifted low-order bits from the current source word
           t1 == the shifted high-order bits from the previous source word
           t2 == the unshifted current source word

           We further know that t2 does not contain a null terminator.  */

        .align 4
$u_loop:
        or      t0, t1, t0      # E : current dst word now complete
        subq    a2, 1, a2       # E : decrement word count
        extql   t2, a1, t1      # U : extract low bits for next time
        addq    a0, 8, a0       # E :

        stq_u   t0, -8(a0)      # U : save the current word
        beq     a2, $u_eoc      # U :
        ldq_u   t2, 8(a1)       # U : Latency=3 load high word for next time
        addq    a1, 8, a1       # E :

        extqh   t2, a1, t0      # U : extract low bits (2 cycle stall)
        cmpbge  zero, t2, t8    # E : test new word for eos
        nop
        beq     t8, $u_loop     # U :

        /* We've found a zero somewhere in the source word we just read.
           If it resides in the lower half, we have one (probably partial)
           word to write out, and if it resides in the upper half, we
           have one full and one partial word left to write out.

           On entry to this basic block:
           t0 == the shifted low-order bits from the current source word
           t1 == the shifted high-order bits from the previous source word
           t2 == the unshifted current source word.  */
$u_eos:
        or      t0, t1, t0      # E : first (partial) source word complete
        nop
        cmpbge  zero, t0, t8    # E : is the null in this first bit? (stall)
        bne     t8, $u_final    # U : (stall)

        stq_u   t0, 0(a0)       # L : the null was in the high-order bits
        addq    a0, 8, a0       # E :
        subq    a2, 1, a2       # E :
        nop

$u_late_head_exit:
        extql   t2, a1, t0      # U :
        cmpbge  zero, t0, t8    # E :
        or      t8, t10, t6     # E : (stall)
        cmoveq  a2, t6, t8      # E : Latency=2, extra map slot (stall)

        /* Take care of a final (probably partial) result word.
           On entry to this basic block:
           t0 == assembled source word
           t8 == cmpbge mask that found the null.  */
$u_final:
        negq    t8, t6          # E : isolate low bit set
        and     t6, t8, t12     # E : (stall)
        and     t12, 0x80, t6   # E : avoid dest word load if we can (stall)
        bne     t6, 1f          # U : (stall)

        ldq_u   t1, 0(a0)       # L :
        subq    t12, 1, t6      # E :
        or      t6, t12, t8     # E : (stall)
        zapnot  t0, t8, t0      # U : kill source bytes > null

        zap     t1, t8, t1      # U : kill dest bytes <= null
        or      t0, t1, t0      # E : (stall)
        nop
        nop

1:      stq_u   t0, 0(a0)       # L :
        ret     (t9)            # L0 : Latency=3

          /* Got to end-of-count before end of string.  
             On entry to this basic block:
             t1 == the shifted high-order bits from the previous source word  */
$u_eoc:
        and     a1, 7, t6       # E : avoid final load if possible
        sll     t10, t6, t6     # U : (stall)
        and     t6, 0xff, t6    # E : (stall)
        bne     t6, 1f          # U : (stall)

        ldq_u   t2, 8(a1)       # L : load final src word
        nop
        extqh   t2, a1, t0      # U : extract low bits for last word (stall)
        or      t1, t0, t1      # E : (stall)

1:      cmpbge  zero, t1, t8    # E :
        mov     t1, t0          # E :

$u_eocfin:                      # end-of-count, final word
        or      t10, t8, t8     # E :
        br      $u_final        # L0 : Latency=3

        /* Unaligned copy entry point.  */
        .align 4
$unaligned:

        ldq_u   t1, 0(a1)       # L : load first source word
        and     a0, 7, t4       # E : find dest misalignment
        and     a1, 7, t5       # E : find src misalignment
        /* Conditionally load the first destination word and a bytemask
           with 0xff indicating that the destination byte is sacrosanct.  */
        mov     zero, t0        # E :

        mov     zero, t6        # E :
        beq     t4, 1f          # U :
        ldq_u   t0, 0(a0)       # L :
        lda     t6, -1          # E :

        mskql   t6, a0, t6      # U :
        nop
        nop
        subq    a1, t4, a1      # E : sub dest misalignment from src addr

        /* If source misalignment is larger than dest misalignment, we need
           extra startup checks to avoid SEGV.  */

1:      cmplt   t4, t5, t12     # E :
        extql   t1, a1, t1      # U : shift src into place
        lda     t2, -1          # E : for creating masks later
        beq     t12, $u_head    # U : (stall)

        extql   t2, a1, t2      # U :
        cmpbge  zero, t1, t8    # E : is there a zero?
        andnot  t2, t6, t2      # E : dest mask for a single word copy
        or      t8, t10, t5     # E : test for end-of-count too

        cmpbge  zero, t2, t3    # E :
        cmoveq  a2, t5, t8      # E : Latency=2, extra map slot
        nop                     # E : keep with cmoveq
        andnot  t8, t3, t8      # E : (stall)

        beq     t8, $u_head     # U :
        /* At this point we've found a zero in the first partial word of
           the source.  We need to isolate the valid source data and mask
           it into the original destination data.  (Incidentally, we know
           that we'll need at least one byte of that original dest word.) */
        ldq_u   t0, 0(a0)       # L :
        negq    t8, t6          # E : build bitmask of bytes <= zero
        mskqh   t1, t4, t1      # U :

        and     t6, t8, t12     # E :
        subq    t12, 1, t6      # E : (stall)
        or      t6, t12, t8     # E : (stall)
        zapnot  t2, t8, t2      # U : prepare source word; mirror changes (stall)

        zapnot  t1, t8, t1      # U : to source validity mask
        andnot  t0, t2, t0      # E : zero place for source to reside
        or      t0, t1, t0      # E : and put it there (stall both t0, t1)
        stq_u   t0, 0(a0)       # L : (stall)

        ret     (t9)            # L0 : Latency=3
        nop
        nop
        nop

        .end __stxncpy